Skip to content

SecureAI-Team/awesome-aisecurity

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Awesome AI Security Awesome

Curated resources for securing AI/ML systems across threat modeling, adversarial ML, LLM security, governance, MLSecOps, and benchmarks.

Read this in other languages: 中文

Contributions welcome! See CONTRIBUTING for details.


Contents


?? ASB Open Source Ecosystem

  • ASB Security Schema - Unified JSON schema for capturing AI security telemetry and sharing alerts across systems.
  • asb-secure-gateway - Reference gateway enforcing ASB schema with OPA policies for AI-native traffic.

Quick Start

  1. Map the threat landscape: skim Section 1 before picking tools or controls.
  2. Experiment with adversarial tooling: start with the libraries in Section 2 to understand attacker capability.
  3. Secure LLM applications: apply the guidance and scanners in Section 3 as you build guardrails.
  4. Embed governance early: use the risk and privacy references in Section 4 to keep regulators happy.
  5. Operationalize safeguards: treat Section 5 as your MLSecOps checklist.

1. Threat Modeling & Frameworks

1.1 General AI/ML Threat Modeling

1.2 Risk Management, Governance & Standards


2. Adversarial Machine Learning

2.1 Toolkits & Libraries

  • Adversarial Robustness Toolbox (ART) - Python library for evasion, poisoning, extraction, and inference attacks plus defenses.
  • CleverHans - Classic adversarial example framework for benchmarking robustness.
  • Foolbox - Unified interface for fast gradient-based and decision-based attacks across DL frameworks.
  • AdvBox - Attack generation across CV, NLP, and speech models with multi-framework support.
  • TextAttack - NLP-focused adversarial attack, augmentation, and training library.
  • AutoAttack - Parameter-free ensemble of strong white-box attacks for reliable robustness evaluation.

2.2 Research & Surveys


3. LLM & GenAI Security

3.1 Guidance & Taxonomies

3.2 Tools & Frameworks

  • garak - LLM vulnerability scanner probing for jailbreaks, leakage, and safety failures.
  • LLM Guard - Input/output filtering toolkit with regex, classifiers, and secret detectors for LLM apps.
  • DeepTeam - Red teaming orchestration framework for multi-agent LLM penetration testing.
  • Giskard - Evaluation suite catching bias, robustness, and security issues in ML/LLM pipelines.
  • cyber-security-llm-agents - AutoGen-based agents for offensive and defensive AI security tasks.

Need LLM jailbreak benchmarks? Jump to Section 6.2.


4. Privacy, Safety & Governance


5. MLSecOps, MLOps & Supply Chain Security


6. Datasets & Benchmarks

6.1 Robustness to Corruptions & Perturbations

  • ImageNet-C - Standard corruption benchmark to evaluate ML robustness to common noise patterns.
  • CIFAR-10-C / CIFAR-100-C - Corruption suites for CIFAR datasets spanning 19 perturbations at five severities.
  • RobustBench - Leaderboard and library for adversarially robust models plus evaluation scripts.

6.2 LLM Jailbreak & Safety Benchmarks


7. Learning Resources


9. Related Awesome Lists


Contributing

We welcome high-signal resources that directly improve the security of AI systems.

What we accept

  • Threat modeling frameworks, governance standards, and incident handling references.
  • Offensive and defensive research (adversarial ML, jailbreaks, poisoning, extraction, inference, safety testing).
  • Production-ready tooling, datasets, benchmarks, and red teaming harnesses.
  • Tutorials, talks, and books that teach practitioners how to secure AI systems.

Formatting rules

  1. Use unordered list items (-) and keep one resource per line.
  2. Follow the format below and keep descriptions concise and plain English.

Tools / libraries

- [Project Name](https://example.com) - One-line description of what it does and why its useful.

Papers / posts / datasets

- *Paper or Post Title* - Short summary plus venue or publisher if relevant.

Add new entries near related content sections to keep the list curated and deduplicated. Please also double-check that added links are live and publicly accessible.


Project Status & Roadmap

This list is early-stage and intentionally scoped to core security primitives. Near-term goals:

  • Expand domains beyond generic ML/LLM (healthcare, industrial, safety-critical control).
  • Track emerging GenAI-specific benchmarks and red teaming playbooks.
  • Highlight production case studies once vetted.

Issues and PRs are welcome for suggestions.


License

This project is released under CC0 1.0. You can copy, modify, and reuse the list without asking permission.

Releases

No releases published

Packages

No packages published